I training the multilabel classifier using the RBF network. I want to choose between different loss functions. I looked at a bunch of documentation about the different loss functions but can't get an intuitive sense of when to use one over the others. I can't decide between hinge loss, correntropy (c-loss) and SLS loss functions. also I can't find any good document to explain SLS and ASLS loss function.
here is the picture of these loss functions which I find in this paper
considering that I use passive aggrasive method for updating weights which one of these functions is better? I realize this is a short question, but not quite sure what other information to provide.